Re: [PATCH 6/9] cpu/SMT: Allow enabling partial SMT states via sysfs

From
Thomas Gleixner <hidden>
Date
2023-06-10 20:09:54
Also in
linux-arch, lkml
Reply to
Michael Ellerman, 2023-05-24
On Thu, May 25 2023 at 01:56, Michael Ellerman wrote:
There is a hook which allows arch code to control how many threads per
Can you please write out architecture in changelogs and comments?

I know 'arch' is commonly used but while my brain parser tolerates
'arch_' prefixes it raises an exception on 'arch' in prose as 'arch' is
a regular word with a completely different meaning. Changelogs and
comments are not space constraint.
quoted hunk ↗ jump to hunk
@@ -2505,20 +2505,38 @@ __store_smt_control(struct device *dev, struct device_attribute *attr,
 	if (cpu_smt_control == CPU_SMT_NOT_SUPPORTED)
 		return -ENODEV;
 
-	if (sysfs_streq(buf, "on"))
+	if (sysfs_streq(buf, "on")) {
 		ctrlval = CPU_SMT_ENABLED;
-	else if (sysfs_streq(buf, "off"))
+		num_threads = cpu_smt_max_threads;
+	} else if (sysfs_streq(buf, "off")) {
 		ctrlval = CPU_SMT_DISABLED;
-	else if (sysfs_streq(buf, "forceoff"))
+		num_threads = 1;
+	} else if (sysfs_streq(buf, "forceoff")) {
 		ctrlval = CPU_SMT_FORCE_DISABLED;
-	else
+		num_threads = 1;
+	} else if (kstrtoint(buf, 10, &num_threads) == 0) {
+		if (num_threads == 1)
+			ctrlval = CPU_SMT_DISABLED;
+		else if (num_threads > 1 && topology_smt_threads_supported(num_threads))
+			ctrlval = CPU_SMT_ENABLED;
+		else
+			return -EINVAL;
+	} else {
 		return -EINVAL;
+	}
 
 	ret = lock_device_hotplug_sysfs();
 	if (ret)
 		return ret;
 
-	if (ctrlval != cpu_smt_control) {
+	orig_threads = cpu_smt_num_threads;
+	cpu_smt_num_threads = num_threads;
+
+	if (num_threads > orig_threads) {
+		ret = cpuhp_smt_enable();
+	} else if (num_threads < orig_threads) {
+		ret = cpuhp_smt_disable(ctrlval);
+	} else if (ctrlval != cpu_smt_control) {
 		switch (ctrlval) {
 		case CPU_SMT_ENABLED:
 			ret = cpuhp_smt_enable();
This switch case does not make sense anymore.

The only situation which reaches this is when the control value goes
from CPU_SMT_DISABLED to CPU_SMT_FORCE_DISABLED because that's not
changing the number of threads.

So something like this is completely sufficient:

	if (num_threads > orig_threads)
		ret = cpuhp_smt_enable();
        else if (num_threads < orig_threads || ctrval == CPU_SMT_FORCE_DISABLED)
		ret = cpuhp_smt_disable(ctrlval);

No?

Thanks,

        tglx
Thread (23 messages) 23 messages, 3 authors, last reply 2023-06-14
Keyboard shortcuts
hback out one level
jnext message in thread / next series-diff position
kprevious message in thread / previous series-diff position
ldrill in
Escclose help / fold thread tree
?toggle this help